Related papers: ReGate: Enabling Power Gating in Neural Processing…
Spiking neural networks (SNNs) are the third generation of neural networks and can explore both rate and temporal coding for energy-efficient event-driven computation. However, the decision accuracy of existing SNN designs is contingent…
Many recent papers have demonstrated fast in-network computation using programmable switches, running many orders of magnitude faster than CPUs. The main limitation of writing software for switches is the constrained programming model and…
This paper proposes a hardware-oriented dropout algorithm, which is efficient for field programmable gate array (FPGA) implementation. In deep neural networks (DNNs), overfitting occurs when networks are overtrained and adapt too well to…
Accurate power load forecasting is crucial for improving energy efficiency and ensuring power supply quality. Considering the power load forecasting problem involves not only dynamic factors like historical load variations but also static…
The magnitude of the real-time digital signal processing challenge attached to large radio astronomical antenna arrays motivates use of high performance computing (HPC) systems. The need for high power efficiency (performance per watt) at…
In the design flow of integrated circuits, chip-level verification is an important step that sanity checks the performance is as expected. Power grid verification is one of the most expensive and time-consuming steps of chip-level…
As AI workloads drive increases in datacenter power consumption, accurate GPU power estimation is critical for proactive power management. However, existing power models face a scalability bottleneck not in the modeling techniques…
As dynamic random access memory (DRAM) and other current transistor-based memories approach their scalability limits, the search for alternative storage methods becomes increasingly urgent. Phase-change memory (PCM) emerges as a promising…
Recurrent neural networks (RNNs) are valued for their computational efficiency and reduced memory requirements on tasks involving long sequence lengths but require high memory-processor bandwidth to train. Checkpointing techniques can…
Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. However, their hefty computational and memory demands make them challenging to deploy to…
Many architects believe that major improvements in cost-energy-performance must now come from domain-specific hardware. This paper evaluates a custom ASIC---called a Tensor Processing Unit (TPU)---deployed in datacenters since 2015 that…
Due to embedded systems` stringent design constraints, much prior work focused on optimizing energy consumption and/or performance. Since embedded systems typically have fewer cooling options, rising temperature, and thus temperature…
Fine-grained power monitoring of software activities becomes unavoidable to maximize the power usage efficiency of data centers. In particular, achieving an optimal scheduling of containers requires the deployment of software-defined…
Much recent research is devoted to exploring tradeoffs between computational accuracy and energy efficiency at different levels of the system stack. Approximation at the floating point unit (FPU) allows saving energy by simply reducing the…
Although we may be at the end of Moore's law, lowering chip power consumption is still the primary driving force for the designers. To enable low-power operation, we propose a resonant energy recovery static random access memory (SRAM). We…
Deep Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in a wide range of applications. However, deeper CNN models, which are usually computation consuming, are widely required for complex Artificial…
Graphics Processing Units (GPUs) were once used solely for graphical computation tasks but with the increase in the use of machine learning applications, the use of GPUs to perform general-purpose computing has increased in the last few…
High energy consumption of artificial intelligence has gained momentum worldwide, which necessitates major investments on expanding efficient and carbon-neutral generation and data center infrastructure in electric power grids. Going beyond…
In recent decades, High Performance Computing (HPC) has undergone significant enhancements, particularly in the realm of hardware platforms, aimed at delivering increased processing power while keeping power consumption within reasonable…
Neuromorphic hardware platforms can significantly lower the energy overhead of a machine learning inference task. We present a design-technology tradeoff analysis to implement such inference tasks on the processing elements (PEs) of a Non-…